SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.00701 · NeurIPS · 2020

Locally Differentially Private (Contextual) Bandits Learning

Liwei Wang, Kai Zheng, Weiran Huang, Zhenguo Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We study locally differentially private (LDP) bandits learning in this paper. First, we propose simple black-box reduction frameworks that can solve a large family of context-free bandits learning problems with LDP guarantee. Based on our frameworks, we can improve previous best results for private bandits learning with one-point feedback, such as private Bandits Convex Optimization, and obtain the first result for Bandits Convex Optimization (BCO) with multi-point feedback under LDP. LDP guarantee and black-box nature make our frameworks more attractive in real applications compared with previous specifically designed and relatively weaker differentially private (DP) context-free bandits algorithms. Further, we extend our (ε, δ)-LDP algorithm to Generalized Linear Bandits, which enjoys a sub-linear regret Õ(T 3/4 /ε) and is conjectured to be nearly optimal. Note that given the existing Ω(T ) lower bound for DP contextual linear bandits [35], our result shows a fundamental difference between LDP and DP contextual bandits learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.00701")
get_code_for_paper("2006.00701")
have("2006.00701")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.00701.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.00701.svg)](https://syntology.ai/paper/2006.00701)

Connect an agent — have() is free.